.png){kind=icon}
返回
Learning and approximation capabilities of orthogonal super greedy algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2015.12.011.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We consider the approximation capability of orthogonal super greedy algorithms (OSGA) and its applications in supervised learning. OSGA focuses on selecting more than one atoms in each iteration, which, of course, reduces the computational burden when compared with the conventional orthogonal greedy algorithm (OGA). We prove that even for function classes that are not the convex hull of the dictionary, OSGA does not degrade the approximation capability of OGA, provided the dictionary is incoherent. Based on this, we deduce tight generalization error bounds for OSGA learning. Our results show that in the realm of supervised learning, OSGA provides a possibility to further reduce the computational burden of OGA on the premise of maintaining its prominent generalization capability. (C) 2015 Elsevier B.V. All rights reserved.
Keyword:
Supervised learning
Nonlinear approximation
Orthogonal super greedy algorithm
Orthogonal greedy algorithm
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
Valuation of Travel Time and Traveller Information in Multimodal Personal Travel under Uncertainty
PREAI
分享收藏The role of serum procalcitonin in establishing the diagnosis and prognosis of pleural infection
OAAI
OAAI分享收藏Post-dissociation interactions in ESD: The 18O−C16O surface reactions induced by 4–10 eV electrons
PREAI
分享收藏
查看更多内容